Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12642
    Prev
    Next
    INDEX
    Explanations

    key parameters related to chart configuration and manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.81
    expandindo
    -0.75
    SequentialGroup
    -0.70
     Италијани
    -0.70
    HtmlAttribute
    -0.70
    AndEndTag
    -0.69
    IUrlHelper
    -0.68
    __*/
    -0.68
    ыгана
    -0.66
    tagHelperRunner
    -0.65
    POSITIVE LOGITS
     المعيارى
    0.59
    fendi
    0.54
    ɨ
    0.49
     sáb
    0.48
     ADDITIONAL
    0.48
    additional
    0.48
     appareil
    0.48
     hề
    0.47
    vlá
    0.47
    Additional
    0.47
    Activations Density 0.446%

    No Known Activations